{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T19:49:11Z","timestamp":1791575351677,"version":"4.3.4"},"reference-count":20,"publisher":"Oxford University Press (OUP)","issue":"5","license":[{"start":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Artificial intelligence (AI) is increasingly being integrated into oncology for applications including cancer detection, risk stratification, treatment planning, and clinical documentation. Concerningly, growing evidence demonstrates that AI systems can reproduce or amplify existing disparities across patient populations. Although considerable effort has focused on developing computational methods to reduce algorithmic bias, many challenges surrounding fairness extend beyond technical implementation. In this commentary, we examine algorithmic fairness in oncology from technical and normative perspectives. We review common sources of bias throughout the machine-learning pipeline; discuss major statistical definitions of fairness, including demographic parity, calibration, and equalized odds; and highlight the inherent trade-offs among these metrics. We further explore how fairness often conflicts with overall predictive performance, arguing that model selection inevitably reflects ethical judgments rather than purely technical optimization. We discuss the limitations of current bias mitigation strategies and contend that many disparities rooted in historical and structural inequities cannot be resolved through algorithmic interventions alone. Finally, we outline priorities for the responsible development and deployment of clinical AI, including greater transparency in fairness decisions, context-specific evaluation standards, ongoing postdeployment auditing, and stronger regulatory oversight. Achieving equitable AI in oncology will require coordinated efforts among developers, clinicians, regulators, and patients to ensure that these technologies improve outcomes without perpetuating existing inequities.<\/jats:p>","DOI":"10.1093\/jncics\/pkag081","type":"journal-article","created":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T12:49:49Z","timestamp":1786798189000},"source":"Crossref","is-referenced-by-count":1,"title":["Challenges in medical algorithmic fairness"],"prefix":"10.1093","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-8523-2897","authenticated-orcid":false,"given":"Anand","family":"Srinivasan","sequence":"first","affiliation":[{"name":"Department of Therapeutic Radiology, Yale School of Medicine , New Haven, CT,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6553-209X","authenticated-orcid":false,"given":"Durga V","family":"Sritharan","sequence":"additional","affiliation":[{"name":"Department of Therapeutic Radiology, Yale School of Medicine , New Haven, CT,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5681-7528","authenticated-orcid":false,"given":"Sanjay","family":"Aneja","sequence":"additional","affiliation":[{"name":"Department of Therapeutic Radiology, Yale School of Medicine , New Haven, CT,","place":["United States"]},{"name":"Center for Outcomes Research and Evaluation, Yale New Haven Hospital , New Haven, CT,","place":["United States"]},{"name":"Department of Biomedical Informatics and Data Science, Yale School of Medicine , New Haven, CT,","place":["United States"]},{"name":"Department of Biomedical Engineering, Yale University , New Haven, CT,","place":["United States"]},{"name":"Yale School of Medicine Yale Cancer Center, , New Haven, CT,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7438-8907","authenticated-orcid":false,"given":"Ilana B","family":"Richman","sequence":"additional","affiliation":[{"name":"Section of General Internal Medicine, Yale School of Medicine , New Haven, CT,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,8,17]]},"reference":[{"key":"2026100914520929600_pkag081-B1","author":"Health, C. for D. and R","year":"2026"},{"key":"2026100914520929600_pkag081-B2","doi-asserted-by":"publisher","first-page":"951","DOI":"10.3390\/biomedicines13040951","article-title":"Artificial intelligence advancements in oncology: a review of current trends and future directions","volume":"13","author":"Huhulea","year":"2025","journal-title":"Biomedicines"},{"key":"2026100914520929600_pkag081-B3","doi-asserted-by":"publisher","first-page":"2760","DOI":"10.3390\/diagnostics13172760","article-title":"Redefining radiology: a review of artificial intelligence integration in medical imaging","volume":"13","author":"Najjar","year":"2023","journal-title":"Diagnostics"},{"key":"2026100914520929600_pkag081-B4","doi-asserted-by":"publisher","first-page":"e2616556","DOI":"10.1001\/jamanetworkopen.2026.16556","article-title":"Physician-reported safety outcomes of AI-generated hospital course summaries","volume":"9","author":"Grolleau","year":"2026","journal-title":"JAMA Netw Open"},{"key":"2026100914520929600_pkag081-B5","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1126\/science.aax2342","article-title":"Dissecting racial bias in an algorithm used to manage the health of populations","volume":"366","author":"Obermeyer","year":"2019","journal-title":"Science"},{"key":"2026100914520929600_pkag081-B6","doi-asserted-by":"publisher","author":"Zong","year":"2023","DOI":"10.48550\/arXiv.2210.01725"},{"key":"2026100914520929600_pkag081-B7","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1186\/s12911-025-03118-0","article-title":"Evaluating gender bias in large language models in long-term care","volume":"25","author":"Rickman","year":"2025","journal-title":"BMC Med Inform Decis Mak"},{"key":"2026100914520929600_pkag081-B8","volume-title":"Fairness and Machine Learning","author":"Barocas","year":"2023"},{"key":"2026100914520929600_pkag081-B9","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1377\/hlthaff.2021.01423","article-title":"Negative patient descriptors: documenting racial bias in the electronic health record","volume":"41","author":"Sun","year":"2022","journal-title":"Health Aff. (Millwood)"},{"key":"2026100914520929600_pkag081-B10","doi-asserted-by":"publisher","first-page":"e2438550","DOI":"10.1001\/jamanetworkopen.2024.38550","article-title":"Race and ethnicity and clinician linguistic expressions of doubt in hospital admission notes","volume":"7","author":"Lee","year":"2024","journal-title":"JAMA Netw Open"},{"key":"2026100914520929600_pkag081-B11","doi-asserted-by":"publisher","first-page":"e65317","DOI":"10.2196\/65317","article-title":"Evaluation and bias analysis of large language models in generating synthetic electronic health records: comparative study","volume":"27","author":"Huang","year":"2025","journal-title":"J Med Internet Res"},{"key":"2026100914520929600_pkag081-B12","doi-asserted-by":"publisher","author":"Kleinberg","year":"2016","DOI":"10.48550\/arXiv.1609.05807"},{"key":"2026100914520929600_pkag081-B13","doi-asserted-by":"publisher","author":"Zhong","DOI":"10.1109\/ISIT57864.2024.10619526"},{"key":"2026100914520929600_pkag081-B14","doi-asserted-by":"crossref","DOI":"10.4159\/9780674042605","volume-title":"A Theory of Justice","author":"Rawls","year":"1971"},{"key":"2026100914520929600_pkag081-B15","author":"Mill","year":"2009"},{"key":"2026100914520929600_pkag081-B16","doi-asserted-by":"publisher","first-page":"e406","DOI":"10.1016\/S2589-7500(22)00063-2","article-title":"AI recognition of patient race in medical imaging: a modelling study","volume":"4","author":"Gichoya","year":"2022","journal-title":"Lancet Digit Health"},{"key":"2026100914520929600_pkag081-B17","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1007\/s44248-024-00007-1","article-title":"Towards a holistic view of bias in machine learning: bridging algorithmic fairness and imbalanced learning","volume":"2","author":"Dablain","year":"2024","journal-title":"Discov Data"},{"key":"2026100914520929600_pkag081-B18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3616865","article-title":"Fairness in machine learning: a survey","volume":"56","author":"Caton","year":"2024","journal-title":"ACM Comput Surv"},{"key":"2026100914520929600_pkag081-B19","doi-asserted-by":"publisher","first-page":"104544","DOI":"10.1016\/j.jbi.2023.104544","article-title":"Fair patient model: mitigating bias in the patient representation learned from the electronic health records","volume":"148","author":"Sivarajkumar","year":"2023","journal-title":"J Biomed Inform"},{"key":"2026100914520929600_pkag081-B20","journal-title":"Software as a Medical Device (SaMD)"}],"container-title":["JNCI Cancer Spectrum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jncics\/advance-article-pdf\/doi\/10.1093\/jncics\/pkag081\/70666045\/pkag081.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jncics\/article-pdf\/10\/5\/pkag081\/70666045\/pkag081.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jncics\/article-pdf\/10\/5\/pkag081\/70666045\/pkag081.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T18:52:12Z","timestamp":1791571932000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jncics\/article\/doi\/10.1093\/jncics\/pkag081\/8762641"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,17]]},"references-count":20,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,9,3]]}},"URL":"https:\/\/doi.org\/10.1093\/jncics\/pkag081","relation":{},"ISSN":["2515-5091"],"issn-type":[{"value":"2515-5091","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,10]]},"published":{"date-parts":[[2026,8,17]]},"article-number":"pkag081"}}